Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to individuals or businesses

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names, primarily focusing on "Nob"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gutenberg
    -0.80
     Nadu
    -0.78
    ocker
    -0.74
     Zeit
    -0.71
    ization
    -0.68
    EngineDebug
    -0.67
    Angelo
    -0.67
    é»Ĵ
    -0.67
    xual
    -0.67
     Gazette
    -0.67
    POSITIVE LOGITS
    leness
    1.05
    uilt
    0.96
    lich
    0.95
    rants
    0.95
    ility
    0.95
    odies
    0.95
    aido
    0.94
    bey
    0.93
    rig
    0.89
    lisher
    0.87
    Act Density 0.017%

    No Known Activations